Development of a data acquisition method to train neural networks to diagnose gas turbine engines and gas pumping units

Abstract

<p>The application of neural networks is one of promising ways to improve efficiency when diagnosing aviation gas turbine engines and gas pumping units. In order to start functioning of such network, it should be trained first using the pre-defined training sets. These data should fully characterize work of the object in a wide range of operating modes and at various technical states of the diagnosticated assemblies. In addition, it is necessary to have a similar data set to monitor quality of the neural network learning.</p><p>To train the network to recognize faults of one type, a set of 20‒200 or more training examples is required. Obtaining such information in operation or in full-scale tests is a rather long or costly process.</p><p>A method for acquisition of training and control data sets was proposed. The sets are intended to train static neural networks recognizing single and multiple faults of the elements of air-gas channels of gas turbine engines and gas pumping units. The method enables obtaining sets of working process parameters describing operation of objects at various technical states of an air-gas channel, effect of measurement errors and object functioning in a wide range of modes and external conditions. Composition of the pumped gas is additionally taken into account for gas pumping units.</p><p>To obtain the required parameters, a mathematical model of the working process of the object of the second level of complexity was used.</p><p>The sets characterize work of operable objects and objects with significant malfunctions in spools of compressors and turbines and in a combustion chamber and for the case of a gas pumping unit, in its supercharger.</p>Two variants of formation of sets were considered: using the measured parameters of the working process; deviations of the measured parameters from their reference values and the parameters used as regime parameters in the mathematical model of the working process. For the second variant, check of expediency of including the regime parameters in the sets was made. It has been shown that regime parameters can be excluded from data sets in some cases

Authors and Affiliations

Mykola Kulyk, Parviz Abdullayev, Oleksandr Yakushenko, Azer Mirzoyev, Oleg Chumak, Valerii Okhmakevych

Keywords

Related Articles

The method for evaluation of educational environment subjects' performance based on the calculation of volumes of m­simplexes

<p class="a">We propose the method for comprehensive performance evaluation of subjects of educational environments, specifically higher educational institutions, based on calculation of generalized volume of the m-simpl...

Hydrothermal mode of the flow­through reservoir­cooler with respect to its morphometric changes

<p>We carried out hydrothermal investigations of the flow-through reservoir-cooler with running water of the thermal power plant. The purpose of the study was to investigate a degree of silting of the flow-through reserv...

Exponential and hyperbolic types of distribution in macrosystems: their combined symmetry and finite properties

<p>This paper proposes the extended entropy method that identifies certain new relations in the organization of macro systems and which sheds light on several existing theoretical issues. It is shown that the type of dis...

Development of information technology elements for decision-making support aimed at re-structuring production at virtual instrument-making enterprises

This paper considers issues related to the re-structuring of virtual industrial enterprises, in particular the prospects for developing a virtual instrument-making enterprise (VIE). Such enterprises operate by employing...

Study into effect of food fibers on the fermentation process of whey

We report the results of research on the effect of food fibers on the fermentation process of whey – the base of beverages. By using the method of IR spectroscopy, we studied various forms of moisture bonds of apple pect...

Download PDF file
  • EP ID EP528312
  • DOI 10.15587/1729-4061.2018.147720
  • Views 64
  • Downloads 0

How To Cite

Mykola Kulyk, Parviz Abdullayev, Oleksandr Yakushenko, Azer Mirzoyev, Oleg Chumak, Valerii Okhmakevych (2018). Development of a data acquisition method to train neural networks to diagnose gas turbine engines and gas pumping units. Восточно-Европейский журнал передовых технологий, 6(9), 55-63. https://europub.co.uk/articles/-A-528312